{"id":"W4383560525","doi":"10.54254/2755-2721/6/20230836","title":"Comparing the effect of CNN and linear regression on facial expression recognition","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kamloops Art Gallery","funders":"","keywords":"Convolutional neural network; Computer science; Facial expression; Facial expression recognition; Artificial intelligence; Expression (computer science); Pattern recognition (psychology); Linear regression; Regression; Facial recognition system; Linear model; Machine learning; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002078532,0.0001011586,0.0001206282,0.0001150581,0.0001185845,0.00003828464,0.00009966172,0.00004033943,0.00000148412],"category_scores_gemma":[0.00002136478,0.00006720633,0.00002035601,0.0002144113,0.00001862989,0.00009468521,0.0001151487,0.0001022072,0.00001686111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005010025,"about_ca_system_score_gemma":0.000004499137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001563482,"about_ca_topic_score_gemma":5.76788e-8,"domain_scores_codex":[0.9993578,0.00002016487,0.0001293393,0.0001834525,0.0002004629,0.0001087872],"domain_scores_gemma":[0.9994251,0.0003897574,0.00004632149,0.00007939443,0.00001942613,0.00004004093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000177328,0.00003270094,0.0008987295,0.0003271022,0.00003867731,0.000007615031,0.00137314,0.576959,0.09414741,0.00770474,0.0007315719,0.317602],"study_design_scores_gemma":[0.0006717361,0.0001046474,0.008390606,0.0002336658,0.000005495443,0.000004863067,0.00002546795,0.9445173,0.04385387,0.001898895,0.0001588716,0.0001345459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9380969,0.00002859079,0.06117563,0.0001016533,0.0001018764,0.0001416603,0.00000214715,0.0001376297,0.0002139434],"genre_scores_gemma":[0.9965369,0.00001530147,0.00331375,0.00002650464,0.00004334843,0.00002626159,0.00002649897,0.000006174564,0.000005267168],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3675584,"threshold_uncertainty_score":0.2740594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01484256005732394,"score_gpt":0.2247412191669488,"score_spread":0.2098986591096248,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}